{"url":"/task/visual-prompting","name":"Visual Prompting","slug":"visual-prompting","description_markdown":"Visual Prompting is the task of streamlining computer vision processes by harnessing the power of prompts,\r\ninspired by the breakthroughs of text prompting in NLP. This innovative approach involves using a few visual\r\nprompts to swiftly convert an unlabeled dataset into a deployed model, significantly reducing development time\r\nfor both individual projects and enterprise solutions.","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Medical","url":"/area/medical"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Music","url":"/area/music"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Playing Games","url":"/area/playing-games"},{"name":"Robots","url":"/area/robots"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":127,"papers_with_code":60,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":2},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/10-shot-image-generation","name":"10-shot image generation"},{"url":"/task/prompt-engineering","name":"Prompt Engineering"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":60,"tagged_in_all":127,"items":[{"url":"/paper/segment-anything","title":"Segment Anything","date":"2023-04-05","arxiv_id":"2304.02643","repositories_listed":32,"syntology":{"n":23,"n_ran":8,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/making-large-multimodal-models-understand","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","date":"2023-12-01","arxiv_id":"2312.00784","repositories_listed":4,"syntology":null},{"url":"/paper/set-of-mark-prompting-unleashes-extraordinary","title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","date":"2023-10-17","arxiv_id":"2310.11441","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/visual-in-context-prompting","title":"Visual In-Context Prompting","date":"2023-11-22","arxiv_id":"2311.13601","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":6}},{"url":"/paper/reprogramming-under-constraints-revisiting","title":"Uncovering the Hidden Cost of Model Compression","date":"2023-08-29","arxiv_id":"2308.14969","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/explicit-visual-prompting-for-universal","title":"Explicit Visual Prompting for Universal Foreground Segmentations","date":"2023-05-29","arxiv_id":"2305.18476","repositories_listed":2,"syntology":null},{"url":"/paper/visual-prompting-for-adversarial-robustness","title":"Visual Prompting for Adversarial Robustness","date":"2022-10-12","arxiv_id":"2210.06284","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/stepwise-decomposition-and-dual-stream-focus","title":"Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation","date":"2025-06-07","arxiv_id":"2506.06818","repositories_listed":1,"syntology":null},{"url":"/paper/vision-graph-prompting-via-semantic-low-rank","title":"Vision Graph Prompting via Semantic Low-Rank Decomposition","date":"2025-05-07","arxiv_id":"2505.04121","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/token-coordinated-prompt-attention-is-needed","title":"Token Coordinated Prompt Attention is Needed for Visual Prompting","date":"2025-05-05","arxiv_id":"2505.02406","repositories_listed":1,"syntology":null},{"url":"/paper/towards-online-multi-modal-social-interaction","title":"Towards Online Multi-Modal Social Interaction Understanding","date":"2025-03-25","arxiv_id":"2503.19851","repositories_listed":1,"syntology":null},{"url":"/paper/chameleon-fast-slow-neuro-symbolic-lane","title":"Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction","date":"2025-03-10","arxiv_id":"2503.07485","repositories_listed":1,"syntology":null},{"url":"/paper/towards-ambiguity-free-spatial-foundation","title":"Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity","date":"2025-03-08","arxiv_id":"2503.06014","repositories_listed":1,"syntology":null},{"url":"/paper/lor-vp-low-rank-visual-prompting-for","title":"LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation","date":"2025-02-02","arxiv_id":"2502.00896","repositories_listed":1,"syntology":null},{"url":"/paper/bringing-characters-to-new-stories-training","title":"IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting","date":"2025-01-26","arxiv_id":"2501.15641","repositories_listed":1,"syntology":null},{"url":"/paper/gpt4scene-understand-3d-scenes-from-videos","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","date":"2025-01-02","arxiv_id":"2501.01428","repositories_listed":1,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/selective-visual-prompting-in-vision-mamba","title":"Selective Visual Prompting in Vision Mamba","date":"2024-12-12","arxiv_id":"2412.08947","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/inst-it-boosting-multimodal-instance","title":"Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning","date":"2024-12-04","arxiv_id":"2412.03565","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/improved-gui-grounding-via-iterative","title":"Improved GUI Grounding via Iterative Narrowing","date":"2024-11-18","arxiv_id":"2411.13591","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-human-and-automated-prompting-in","title":"Benchmarking Human and Automated Prompting in the Segment Anything Model","date":"2024-10-29","arxiv_id":"2410.22048","repositories_listed":1,"syntology":null},{"url":"/paper/improving-visual-object-tracking-through","title":"Improving Visual Object Tracking through Visual Prompting","date":"2024-09-27","arxiv_id":"2409.18901","repositories_listed":1,"syntology":null},{"url":"/paper/attention-prompting-on-image-for-large-vision","title":"Attention Prompting on Image for Large Vision-Language Models","date":"2024-09-25","arxiv_id":"2409.17143","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_unverified":4,"n_pointer_only":2}},{"url":"/paper/when-does-visual-prompting-outperform-linear","title":"When Does Visual Prompting Outperform Linear Probing for Vision-Language Models? A Likelihood Perspective","date":"2024-09-03","arxiv_id":"2409.01821","repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-temporal-action-localization-1","title":"Open-Vocabulary Action Localization with Iterative Visual Prompting","date":"2024-08-30","arxiv_id":"2408.17422","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/2408-03043","title":"Targeted Visual Prompting for Medical Visual Question Answering","date":"2024-08-06","arxiv_id":"2408.03043","repositories_listed":1,"syntology":null},{"url":"/paper/earthmarker-a-visual-prompt-learning","title":"EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing","date":"2024-07-18","arxiv_id":"2407.13596","repositories_listed":1,"syntology":null},{"url":"/paper/by-my-eyes-grounding-multimodal-large","title":"By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting","date":"2024-07-15","arxiv_id":"2407.10385","repositories_listed":1,"syntology":null},{"url":"/paper/uicrit-enhancing-automated-design-evaluation","title":"UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset","date":"2024-07-11","arxiv_id":"2407.08850","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-domains-dynamic-solutions-dpcore-for","title":"Dynamic Domains, Dynamic Solutions: DPCore for Continual Test-Time Adaptation","date":"2024-06-15","arxiv_id":"2406.10737","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/ot-vp-optimal-transport-guided-visual","title":"OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation","date":"2024-06-12","arxiv_id":"2407.09498","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_unverified":4,"n_pointer_only":0}}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}